domainlab.algos package

Subpackages

• domainlab.algos.msels package
  • Submodules
  • domainlab.algos.msels.a_model_sel module
    • AMSel
      • AMSel.accept()
      • AMSel.base_update()
      • AMSel.best_te_metric
      • AMSel.best_val_acc
      • AMSel.early_stop()
      • AMSel.if_stop()
      • AMSel.max_es
      • AMSel.model_selection_epoch
      • AMSel.observer4msel
      • AMSel.reset()
      • AMSel.sel_model_te_acc
      • AMSel.update()
      • AMSel.val_threshold
  • domainlab.algos.msels.c_msel_oracle module
    • MSelOracleVisitor
      • MSelOracleVisitor.accept()
      • MSelOracleVisitor.base_update()
      • MSelOracleVisitor.early_stop()
      • MSelOracleVisitor.oracle_last_setpoint_sel_te_acc
  • domainlab.algos.msels.c_msel_tr_loss module
    • MSelTrLoss
      • MSelTrLoss.base_update()
      • MSelTrLoss.early_stop()
      • MSelTrLoss.max_es
      • MSelTrLoss.reset()
  • domainlab.algos.msels.c_msel_val module
    • MSelValPerf
      • MSelValPerf.base_update()
      • MSelValPerf.best_te_metric
      • MSelValPerf.best_val_acc
      • MSelValPerf.reset()
      • MSelValPerf.sel_model_te_acc
  • Module contents
• domainlab.algos.observers package
  • Submodules
  • domainlab.algos.observers.a_observer module
    • AObVisitor
      • AObVisitor.accept()
      • AObVisitor.after_all()
      • AObVisitor.clean_up()
      • AObVisitor.reset()
      • AObVisitor.set_task()
      • AObVisitor.update()
  • domainlab.algos.observers.b_obvisitor module
    • ObVisitor
      • ObVisitor.accept()
      • ObVisitor.after_all()
      • ObVisitor.cal_oracle_perf()
      • ObVisitor.clean_up()
      • ObVisitor.dump_prediction()
      • ObVisitor.str_metric4msel
      • ObVisitor.update()
  • domainlab.algos.observers.c_obvisitor_cleanup module
    • ObVisitorCleanUp
      • ObVisitorCleanUp.accept()
      • ObVisitorCleanUp.after_all()
      • ObVisitorCleanUp.clean_up()
      • ObVisitorCleanUp.model_sel
      • ObVisitorCleanUp.update()
  • domainlab.algos.observers.c_obvisitor_gen module
    • ObVisitorGen
      • ObVisitorGen.after_all()
  • Module contents
• domainlab.algos.trainers package
  • Subpackages
    • domainlab.algos.trainers.compos package
      • Submodules
      • domainlab.algos.trainers.compos.matchdg_args module
      • domainlab.algos.trainers.compos.matchdg_match module
      • domainlab.algos.trainers.compos.matchdg_utils module
      • Module contents
  • Submodules
  • domainlab.algos.trainers.a_trainer module
    • AbstractTrainer
      • AbstractTrainer.after_batch()
      • AbstractTrainer.before_batch()
      • AbstractTrainer.before_tr()
      • AbstractTrainer.cal_reg_loss()
      • AbstractTrainer.cal_reg_loss_over_task_loss_ratio()
      • AbstractTrainer.decoratee
      • AbstractTrainer.dset_decoration_args_algo()
      • AbstractTrainer.extend()
      • AbstractTrainer.get_model()
      • AbstractTrainer.init_business()
      • AbstractTrainer.is_myjob()
      • AbstractTrainer.list_tr_domain_size
      • AbstractTrainer.model
      • AbstractTrainer.name
      • AbstractTrainer.p_na_prefix
      • AbstractTrainer.post_tr()
      • AbstractTrainer.print_parameters()
      • AbstractTrainer.reset()
      • AbstractTrainer.str_metric4msel
      • AbstractTrainer.tr_epoch()
    • mk_opt()
  • domainlab.algos.trainers.args_dial module
    • add_args2parser_dial()
  • domainlab.algos.trainers.args_miro module
    • add_args2parser_miro()
  • domainlab.algos.trainers.hyper_scheduler module
    • HyperSchedulerWarmupExponential
      • HyperSchedulerWarmupExponential.warmup()
    • HyperSchedulerWarmupLinear
      • HyperSchedulerWarmupLinear.set_steps()
      • HyperSchedulerWarmupLinear.warmup()
  • domainlab.algos.trainers.mmd_base module
    • TrainerMMDBase
      • TrainerMMDBase.gaussian_kernel()
      • TrainerMMDBase.mmd()
      • TrainerMMDBase.my_cdist()
  • domainlab.algos.trainers.train_basic module
    • TrainerBasic
      • TrainerBasic.after_epoch()
      • TrainerBasic.before_epoch()
      • TrainerBasic.before_tr()
      • TrainerBasic.cal_loss()
      • TrainerBasic.log_loss()
      • TrainerBasic.tr_batch()
      • TrainerBasic.tr_epoch()
    • list_divide()
  • domainlab.algos.trainers.train_causIRL module
    • TrainerCausalIRL
      • TrainerCausalIRL.gaussian_kernel()
      • TrainerCausalIRL.mmd()
      • TrainerCausalIRL.my_cdist()
      • TrainerCausalIRL.tr_batch()
  • domainlab.algos.trainers.train_coral module
    • TrainerCoral
      • TrainerCoral.cross_domain_mmd()
      • TrainerCoral.tr_epoch()
  • domainlab.algos.trainers.train_dial module
    • TrainerDIAL
      • TrainerDIAL.gen_adversarial()
  • domainlab.algos.trainers.train_ema module
    • TrainerMA
      • TrainerMA.after_epoch()
      • TrainerMA.move_average()
  • domainlab.algos.trainers.train_fishr module
    • TrainerFishr
      • TrainerFishr.cal_dict_variance_grads()
      • TrainerFishr.cal_mean_across_dict()
      • TrainerFishr.cal_power_single_dict()
      • TrainerFishr.tr_epoch()
      • TrainerFishr.var_grads_and_loss()
      • TrainerFishr.variance_between_dict()
  • domainlab.algos.trainers.train_hyper_scheduler module
    • TrainerHyperScheduler
      • TrainerHyperScheduler.before_batch()
      • TrainerHyperScheduler.before_tr()
      • TrainerHyperScheduler.set_scheduler()
      • TrainerHyperScheduler.tr_epoch()
  • domainlab.algos.trainers.train_irm module
    • TrainerIRM
      • TrainerIRM.tr_epoch()
  • domainlab.algos.trainers.train_matchdg module
    • TrainerMatchDG
      • TrainerMatchDG.before_tr()
      • TrainerMatchDG.dset_decoration_args_algo()
      • TrainerMatchDG.init_business()
      • TrainerMatchDG.mk_match_tensor()
      • TrainerMatchDG.tr_batch()
      • TrainerMatchDG.tr_epoch()
    • match_tensor_reshape()
  • domainlab.algos.trainers.train_miro module
    • TrainerMiro
      • TrainerMiro.before_tr()
  • domainlab.algos.trainers.train_miro_model_wraper module
    • TrainerMiroModelWraper
      • TrainerMiroModelWraper.accept()
      • TrainerMiroModelWraper.cal_feat_layers_ref_model()
      • TrainerMiroModelWraper.clear_features()
      • TrainerMiroModelWraper.extract_intermediate_features()
      • TrainerMiroModelWraper.get_shapes()
      • TrainerMiroModelWraper.hook()
      • TrainerMiroModelWraper.hook_ref()
      • TrainerMiroModelWraper.register_feature_storage_hook()
  • domainlab.algos.trainers.train_miro_utils module
    • MeanEncoder
      • MeanEncoder.forward()
    • VarianceEncoder
      • VarianceEncoder.forward()
  • domainlab.algos.trainers.train_mldg module
    • TrainerMLDG
      • TrainerMLDG.before_tr()
      • TrainerMLDG.prepare_ziped_loader()
      • TrainerMLDG.tr_epoch()
  • domainlab.algos.trainers.zoo_trainer module
    • TrainerChainNodeGetter
  • Module contents

Submodules

domainlab.algos.a_algo_builder module

parent class for combing model, trainer, task, observer

class domainlab.algos.a_algo_builder.NodeAlgoBuilder(success_node=None)

Bases: AbstractChainNodeHandler

Base class for Algorithm Builder

extend(node)

Extends the current algorithm builder with a new node.

This method updates the builder by setting the next_model attribute to the specified node.

Parameters:

node – The node to be added to the algorithm builder.

abstract init_business(exp)

combine model, trainer, observer, task

init_next_model(model, exp)

initialize the next model and decorate with current model

is_myjob(request)

Parameters:

request – string

na_prefix = 'NodeAlgoBuilder'

property name

get the name of the algorithm

domainlab.algos.builder_api_model module

build algorithm from API coded model with custom backbone

class domainlab.algos.builder_api_model.NodeAlgoBuilderAPIModel(success_node=None)

Bases: NodeAlgoBuilder

build algorithm from API coded model with custom backbone

init_business(exp)

return trainer, model, observer

domainlab.algos.builder_custom module

domainlab.algos.builder_custom.make_basic_trainer(class_name_model)

make_basic_trainer. :param class_name_model:

domainlab.algos.builder_dann module

builder for Domain Adversarial Neural Network: accept different training scheme

class domainlab.algos.builder_dann.NodeAlgoBuilderDANN(success_node=None)

Bases: NodeAlgoBuilder

init_business(exp)

return trainer, model, observer

reset_aux_net(net_encoder)

reset auxilliary neural network from task note that net_encoder can also be a method like extract_semantic_feat

domainlab.algos.builder_diva module

Builder pattern to build different component for experiment with DIVA

class domainlab.algos.builder_diva.NodeAlgoBuilderDIVA(success_node=None)

Bases: NodeAlgoBuilder

Builder pattern to build different component for experiment with DIVA

get_trainer(args)

chain of responsibility pattern for fetching trainer from dictionary

init_business(exp)

return trainer, model, observer

domainlab.algos.builder_erm module

builder for erm

class domainlab.algos.builder_erm.NodeAlgoBuilderERM(success_node=None)

Bases: NodeAlgoBuilder

builder for erm

init_business(exp)

return trainer, model, observer

domainlab.algos.builder_hduva module

build hduva model, get trainer from cmd arguments

class domainlab.algos.builder_hduva.NodeAlgoBuilderHDUVA(success_node=None)

Bases: NodeAlgoBuilder

init_business(exp)

return trainer, model, observer

domainlab.algos.builder_jigen1 module

builder for JiGen

class domainlab.algos.builder_jigen1.NodeAlgoBuilderJiGen(success_node=None)

Bases: NodeAlgoBuilder

init_business(exp)

return trainer, model, observer

domainlab.algos.utils module

network builder utils

domainlab.algos.utils.split_net_feat_last(net)

split a pytorch module into feature extractor and last layer

domainlab.algos.zoo_algos module

chain of responsibility pattern for algorithm selection

class domainlab.algos.zoo_algos.AlgoBuilderChainNodeGetter(model, apath)

Bases: object

1. Hardcoded chain 3. Return selected node

register_external_node(chain)

if the user specify an external python file to implement the algorithm

Module contents